Scientific skills

12,450 tagged Scientific, measured the same way as everything else here.

Browse within: bioinformatics 260ai-scientist 207LLM 186agents 186biology 170reasoning-language-models 165ai-scientists 164reasoning-agent 164tool-use 164agent 159data-analysis 133cancer-genomics 132computational-biology 132literature-review 120

pytorch-physics

265

xjtulyc/awesome-rosetta-skills

Skill Claude CodeCodex

Physics-informed neural networks, neural ODEs, and data-driven force-field learning using PyTorch, DeepXDE, and torchdiffeq.

not rated 34 4mo ago A 35 tokens

econometrics

266

xiaomihu1992/econometrics-skill

Skill Claude CodeCodex

Causal inference and applied econometric analysis on tabular data, from uploaded-data diagnostics and cleaning advice to treatment-effect estimation and publication-grade applied research design. Use for policy impact, ATE/ATT/LATE/ITT, OLS, propensity scores, IV/2SLS, DID/event studies, RDD, robustness checks…

not rated 34 4mo ago A 109 tokens original MIT

Impertio-Studio/QGIS-Claude-Skill-Package

Skill Claude CodeCodex

Use when planning a spatial analysis workflow, choosing between analysis approaches, or chaining multiple operations. Prevents wrong analysis method selection and suboptimal workflow ordering. Covers vector vs raster decision trees, processing algorithm selection, workflow chaining, CRS/format guidance, and MCP server…

not rated 33 2mo ago A 100 tokens original MIT

data-stats-analysis

268

omicverse/omicclaw

Skill Claude CodeCodex

Perform statistical tests, hypothesis testing, correlation analysis, and multiple testing corrections using scipy and statsmodels. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).

not rated 33 3mo ago A 40 tokens GPL-3.0

InternScience/MolClaw

Skill Claude CodeCodex

PRIMARY tool for all single-structure interaction analysis. MCP-exposed protein–ligand / peptide / protein–protein interaction analysis and Schrödinger-style multi-dimensional visualization. Pure Python/NumPy engine covering 9 interaction types with 2D diagram, 3D PyMOL rendering, residue bar, interface heatmap…

not rated 33 1mo ago A SkillSpector: warn 112 tokens original MIT

amazing-psycoder

270

soupandpsy/amazing-psycoder-skills

Skill Codex

A coordinator for Amazing PsyCoder, a system that turns psychology experiments or experimental data into reviewed code and analysis materials. It sends each request through design, coding, and review stages when the available input requires them.

not rated 33 26d ago A SkillSpector: pass 110 tokens original MIT

evas-sim

271

Arcadia-1/veriloga-skills

Skill Claude CodeCodex

How to use the EVAS Verilog-A behavioral simulator (pip package: evas-sim). Use this skill whenever the user wants to simulate a Verilog-A (.va) model, run a Spectre (.scs) netlist, check simulation feasibility, install evas-sim, or read simulation output (tran.csv, strobe.txt). Trigger on phrases like "simulate…

not rated 33 +1 1mo ago A 119 tokens

single-cell

272

inflexa-ai/inflexa

Skill Claude CodeCodex

Single-cell analysis pipeline covering scRNA-seq, snRNA-seq, and CyTOF (mass cytometry) — QC, normalization, integration, clustering, annotation, differential expression, trajectory, cell communication, and TF activity inference.

not rated 33 today A 50 tokens original Apache-2.0

spicebridge

273

clanker-lover/spicebridge

Skill Claude Code

Circuit design and SPICE simulation assistant. Use when the user asks about circuit design, filters (low-pass, high-pass, bandpass, notch), amplifiers (inverting, differential, instrumentation, summing), voltage dividers, SPICE simulation, AC/DC/transient analysis, schematics, component selection, frequency response…

not rated 32 +1 5mo ago A 90 tokens GPL-3.0

hujizhou35-cmd/journal-cover-letter-tutorial

Skill Codex

Create, revise, benchmark, or check a cover letter for an academic journal submission from manuscript files. Use whenever a user wants a journal submission letter, asks to tailor a cover letter to a target journal, provides manuscript materials and asks for a letter, wants an existing academic cover letter improved…

not rated 32 27d ago A SkillSpector: pass 124 tokens original MIT

register-ldm-task

275

yzailab/Large-Discovery-Models

Skill Codex needs its repo

Scaffold, implement, register, scientifically qualify, and production-check an LDM domain task in this repository. Use when adding or repairing a task adapter, task manifest, experiment.json benchmark contract, proposal-provider capabilities, metric roles, qualification evidence, official evaluation budget, campaign…

not rated 31 +1 15d ago A SkillSpector: pass 86 tokens original MIT

wit

276

deltadbu/WIT-skill

Skill Claude CodeCodex

Apply WIT (Writing Is Thinking) as a human–LLM collaborative scientific reasoning skill for scientific question formulation, finding-driven research planning, next-experiment selection, Results or Discussion review, claim–evidence and reviewer stress tests, manuscript logic audits, deadline closure, and researcher…

not rated 31 +7 changed 6d ago A 93 tokens

awslabs/hcls-agent-skills

Skill Claude CodeCodex ✓ vendor

Reason about clinical data terminology standards — MedDRA hierarchy (LLT→PT→HLT→HLGT→SOC), ICD-10 code structure and grouping, SNOMED CT concept model, LOINC panel relationships, and mapping decisions between systems. Use when the user asks to code adverse events, map diagnoses to ICD-10, choose a coding granularity…

not rated 31 +5 9d ago A 200 tokens MIT-0

stat-writing

278

fuhaoda/stats-paper-writing-agent-skills

Skill Claude CodeCodex

End-to-end statistical writing assistant for LaTeX - draft title/abstract/keywords, expand outlines into sections, audit manuscripts, write reviewer reports and response letters, and scaffold book manuscripts.

not rated 30 6mo ago A 41 tokens

baidubce/skills

Skill Claude CodeCodex

Manage public and hybrid Famou experiments via famou-ctl: submit config.yaml tasks; inspect status, manifests, leaderboards, logs, and reports; fetch ranked or top results; pause, resume, update, continue, cancel, or delete runs; and check account quota or credits. Use for Famou experiment lifecycle and…

not rated 30 1mo ago A SkillSpector: warn 94 tokens original Apache-2.0

economics-ml

280

garroshub/ai-economist-skill

Skill Claude CodeCodex

Use this skill for macroeconomic nowcasting, central-bank policy diagnostics, economics-oriented ML calibration, and validation reports.

not rated 29 +1 1mo ago A SkillSpector: pass 0 tokens original MIT

eniktab/scientific-paper-writer

Skill Claude Code

Full-lifecycle scientific paper writing assistant. Fetches live journal guidelines, AI authorship policy, word limits, citation format, and LaTeX template for any journal before writing. Audits every draft for 25 AI writing patterns. Verifies every citation via web search. Produces publication-ready prose for Nature…

not rated 29 5mo ago A 85 tokens original MIT

ace-rtl

282

NVlabs/ACE-RTL

Skill Claude CodeCodex

Consolidated ACE-RTL skill for running an iterative generator-reflector-coordinator RTL agent on CVDP. Use for CVDP official repo setup with native or Docker environments, no-cheating benchmark runs, role-based external LLM routing, unique outputs logging, task-driven CVDP prompt guidance, and real pass-rate reporting.

not rated 29 +4 1mo ago A 72 tokens

scholar-megasearch

283

TaewoooPark/scholar-megasearch

Skill Codex needs its repo

Massive multi-source academic literature search via subagent orchestration. Fans out parallel searchers across every available scholarly source — arXiv, Semantic Scholar, Crossref, OpenAlex, PubMed/PMC, bioRxiv/medRxiv, DOAJ, CORE, BASE, DBLP, IACR, SSRN, Zenodo, Unpaywall, plus web/GitHub — then deduplicates by…

not rated 28 26d ago A SkillSpector: pass 206 tokens original MIT

bbl21/cst-runtime-cli

Skill Claude CodeCodex

A workflow for optimizing CST simulation parameters through repeated runs and comparisons. CST is engineering software used to simulate electromagnetic designs.

not rated 28 +2 2mo ago A 76 tokens original MIT

craft-of-research

285

ctfysh/craft-of-research

Skill Claude CodeCodex

A bilingual guide for planning research and exploring important scientific questions through Socratic questioning, where questions help clarify ideas and assumptions. It follows the idea that research is a conversation with existing knowledge and other researchers.

not rated 28 +4 1mo ago A 106 tokens

swmm-end-to-end

286

Zhonghao1995/agentic-swmm-workflow

Skill Claude CodeCodex

Top-level orchestration skill for agentic SWMM modelling. Use when an agent needs one entrypoint that decides which module tools to run, in what order, and when to stop, for example to build, run, QA, and optionally calibrate a SWMM case from prepared or partially prepared inputs.

not rated 27 +2 3d ago A SkillSpector: pass 67 tokens original MIT

sentaurus-tcad

287

starlight-w/claude-sentaurus-skill

Skill Claude CodeCodex

End-to-end Sentaurus TCAD simulation workflow skill. Use this whenever the user asks to create, repair, calibrate, run, diagnose, visualize, or document Sentaurus/SWB/SDE/SDevice/SVisual simulations; mentions TCAD, Sentaurus, SWB, swbpy2, gsub, SDE geometry, mesh, SDevice physics, Id-Vg/Id-Vd/BV/HeavyIon/SEB/TID/ESD…

not rated 27 +2 1mo ago A 161 tokens original MIT

ehr-analysis

288

zongtingwei/Bioclaw_Skills_Hub

Skill Claude CodeCodex

End-to-end EHR predictive modeling pipeline with PyHealth, covering dataset loading, task definition, model training, evaluation, calibration, and clinical interpretation.

not rated 26 5mo ago A 33 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: